I'm excited to share that I’ll be joining @Stanford as an assistant professor of computer science in 2020! Thanks everyone who has helped me along the way. Looking forward to exciting research collaborations at @StanfordAILab, @StanfordSVL and @StanfordHAI!
Jiajun Wu
209 posts
- Honored to have received the dissertation award honorable mention. Thanks to my advisors and collaborators for all the guidance and support!Dor Minzer of @the_IAS receives the 2019 ACM Doctoral Dissertation Award for his dissertation, “On Monotonicity Testing and the 2-to-2-Games Conjecture.” Jakub Tarnawski, of @EPFL, and JiaJun Wu (@jiajunwu_cs) of @MIT receive honorable mentions: bit.ly/3j3czbv
- Excited to be part of the journey, and you should, too :)Want to push the limits of where this tech can go and build the products that put it into users' hands? Join us! jobs.ashbyhq.com/worldlabs
- Ever wondered how roses grow and wither in your backyard?🌹 Our latest work on generating 4D temporal object intrinsics lets you explore a rose's entire lifecycle—from birth to death—under any environment light, from any viewpoint, at any moment. Project page:
00:00 - Thrilled to share that I will be joining @umdcs at @UofMaryland as an Assistant Professor late 2024. I am deeply grateful to my incredible mentors, collaborators, colleagues, and friends for all the support and help throughout this long journey!
- Accurate and controllable scene generation has been difficult with natural language alone. You instead need a language for scenes. Introducing the Scene Language — a visual representation for high-quality 3D/4D generation by integrating programs, words, and embeddings — 🧵(1/6)
00:00 - Please submit your papers to 3DV 2025!📢 Exciting news: #3DV2025 is now open for paper submissions, again on OpenReview! 📅 Deadline: August 12, 2025, 23:59 PT 📝 Author guidelines: 3dvconf.github.io/2025/author-gu…
- Now with code!Get a peek into some (surprisingly accurate) 3D scenes generated via the Scene Language—our new scene representation! Now powered by the new Claude 3.5 Sonnet. More examples in our released repo: github.com/zzyunzhi/scene…. Why is the representation effective? (1/3)
GIF
GIF
GIF
GIF - Replying to @elliottszwuCheck out the demo: huggingface.co/spaces/Kyle-Li… More results on the website: kyleleey.github.io/3DFauna/ Great work led by @zizhang_li & @DorLitvak with the amazing team @RayLi234 @zhang_yunzhi @JakabTomas @chrirupp Andrea Vedaldi @jiajunwu_cs PS: @zizhang_li is applying for PhD!!
- Thanks for inviting me. Looking forward to the discussion.#3DGV: Our next speaker is Jiajun Wu @jiajunwu_cs. Title: Surfaces, Objects, Procedures: Integrating Learning and Graphics for 3D Scene Understanding. Oct. 27th, 7:00 PDT. Panelists: Shuran Song and Siddhartha Chaudhuri. Youtube Link: youtube.com/watch?v=-ltAta…
- Excited to be part of the HAI community.Humans effortlessly navigate the physical world through seeing, reasoning, and interacting with objects around us – but how can this be applied to machines? Stanford’s @jiajunwu_cs discusses his recent work on physical scene understanding. bit.ly/2HTmyCm
- Welcome, Manling!I am excited to join @northwesterncs as an assistant professor in Fall24 and @StanfordSVL as a postdoc with @jiajunwu_cs. I cannot say how much I appreciate the help from my advisor @elgreco_winter, references @ShihFuChang @kchonyc @JiaweiHan @kathymckeown and many many people.
- Honored to be involved in this work!Check out our work on unsupervised physical scene graph extraction at #neurips2020 (talk Monday 6pm by @recursus). Great thanks to collabs @jiajunwu_cs @drfeifei and Josh Tenenbaum.
- Replying to @ManlingLi_ @drfeifei and 6 others

















